nvidia/Llama-3.3-70B-Instruct-FP8 download history
nvidia/Llama-3.3-70B-Instruct-FP8 is a 70.6B-parameter model by nvidia. In the last 30 days it was downloaded 7,810 times (1,813 in the last 7 days), and 842,631 times in total.
It ranks #9,773 on the Hub by monthly downloads.
It has 32 likes.
It is a fine-tune of meta-llama/Llama-3.3-70B-Instruct.
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 7,810 | -9% |
| October 2026 | 8,577 | -65% |
| September 2026 | 24,295 | -39% |
| August 2026 | 40,043 | -68% |
| July 2026 | 126,782 | +182% |
| June 2026 | 44,925 | +20% |
| May 2026 | 37,463 | -3% |
| April 2026 | 38,570 | +25% |
| March 2026 | 30,946 | -72% |
| February 2026 | 111,202 | +565% |
| January 2026 | 16,719 | -2% |
| December 2025 | 17,116 | -37% |
Its busiest 30 days so far ended on 2025-09-28, with 185,590 downloads.
Open nvidia/Llama-3.3-70B-Instruct-FP8 on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.